Models and pricing
Pokee Isaac tiers, per-token rates, and how to specify a model.
Tiers
| Model | Input ($/M tokens) | Output ($/M tokens) | Cache read ($/M tokens) |
|---|---|---|---|
pokee-isaac-high-reasoning | $3 | $15 | $0.30 |
pokee-isaac | $0.30 | $5 | $0.10 |
Additional backends (Kimi, GPT-5.5, Gemini) are available per-tenant by contract. Ask Pokee.
How to specify a model
The model field is accepted on both major surfaces:
- Sessions — pass
modelin the body ofPOST /v1/sessions. Locked at session create. - Stateless tool calling — pass
modelon eachPOST /v1/responsescall. Per-request.
# Session with the high-reasoning tier
curl -X POST "$POKEE_API/v1/sessions" \
-H "Authorization: Bearer $POKEE_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "pokee-isaac-high-reasoning"}'
# Stateless call with the cheapest tier
curl -X POST "$POKEE_API/v1/responses" \
-H "Authorization: Bearer $POKEE_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "pokee-isaac", "input": "Summarize this in one sentence: ..."}'If model is omitted, the gateway uses your tenant's default (pokee-isaac-high-reasoning for new tenants).
Tracking spend
Use GET /v1/usage to read your current credit balance. Read balance before and after a call to measure the exact debit.